Run d5aeb478
Jul 10, 2026, 12:41
OpenRouter · 6 models · repeat ×1
d5aeb478-8f9a-4313-8fad-be1c05a93fc0
Downloads
Audit pack
Results
6 models
| # | Adapter | Model | Think | Pass % | Cover % | Score | Outcomes | Time |
|---|---|---|---|---|---|---|---|---|
| 1 | OpenRouter | gpt-oss-20b | Low | 80.0% | 100.0% | 90.0% | 4/1/0/0 | 2.8s |
#1 gpt-oss-20bLowPass rate80.0% 4 pass · 5 scored Coverage100.0% 5 / 5 evidence-bearing Verified score90.0% 95% interval — · 1 run(s) pass@k80.0% 4/5 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures4/5 passed in linked runplayer-iteratorents-iteratorhook-addisvalidnet-receivers | ||||||||
| 2 | OpenRouter | gpt-oss-20b | Medium | 75.0% | 80.0% | 70.0% | 3/1/0/0 | 39.0s |
#2 gpt-oss-20bMediumPass rate75.0% 3 pass · 4 scored Coverage80.0% 4 / 5 evidence-bearing Verified score70.0% 95% interval — · 1 run(s) pass@k75.0% 3/5 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures3/5 passed in linked runents-iteratorplayer-iteratorhook-addisvalidnet-receivers | ||||||||
| 3 | OpenRouter | gpt-oss-120b | Medium | 100.0% | 40.0% | 40.0% | 2/0/0/3 | 8.2s |
#3 gpt-oss-120bMediumPass rate100.0% 2 pass · 2 scored Coverage40.0% 2 / 5 evidence-bearing Verified score40.0% 95% interval — · 1 run(s) pass@k100.0% 2/5 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures2/5 passed in linked runisvalidnet-receiversplayer-iteratorents-iteratorhook-add | ||||||||
| 4 | OpenRouter | gpt-oss-120b | Low | 100.0% | 20.0% | 20.0% | 1/0/0/4 | 5.8s |
#4 gpt-oss-120bLowPass rate100.0% 1 pass · 1 scored Coverage20.0% 1 / 5 evidence-bearing Verified score20.0% 95% interval — · 1 run(s) pass@k100.0% 1/5 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures1/5 passed in linked runhook-addisvalidnet-receiversplayer-iteratorents-iterator | ||||||||
| 5 | OpenRouter | gpt-oss-120b | High | 0.0% | 0.0% | 0.0% | 0/0/0/5 | 2.3s |
#5 gpt-oss-120bHighPass rate0.0% 0 pass · 0 scored Coverage0.0% 0 / 5 evidence-bearing Verified score0.0% 95% interval — · 1 run(s) pass@k0.0% 0/5 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures0/5 passed in linked runents-iteratorhook-addisvalidnet-receiversplayer-iterator | ||||||||
| 6 | OpenRouter | gpt-oss-20b | High | 0.0% | 0.0% | 0.0% | 0/0/0/5 | 11.1s |
#6 gpt-oss-20bHighPass rate0.0% 0 pass · 0 scored Coverage0.0% 0 / 5 evidence-bearing Verified score0.0% 95% interval — · 1 run(s) pass@k0.0% 0/5 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures0/5 passed in linked runents-iteratorhook-addisvalidnet-receiversplayer-iterator | ||||||||
Verified score aggregates compatible runs. Outcomes = pass / partial / wrong / invalid output; harness failures are excluded. Click a row for evidence and the linked run's fixtures.
Fixtures
5
gmod.ents-iterator.v1gmod.hook-add.v1gmod.isvalid.v1gmod.net-receivers.v1gmod.player-iterator.v1